Coseismic landslide susceptibility modelling via machine learning associated with the September 5, 2022, Luding Mw 6.8 earthquake, southeastern Tibetan Plateau.
Saved in:
| Title: | Coseismic landslide susceptibility modelling via machine learning associated with the September 5, 2022, Luding Mw 6.8 earthquake, southeastern Tibetan Plateau. |
|---|---|
| Authors: | Deng, Lin1 (AUTHOR), Wang, Hu1 (AUTHOR) wanghu9905@126.com, Li, Kaijin1 (AUTHOR), Shen, Changwei1 (AUTHOR) |
| Source: | Bulletin of Engineering Geology & the Environment. Apr2026, Vol. 85 Issue 4, p1-15. 15p. |
| Abstract: | Coseismic landslides have been widely studied due to their high occurrence and severe damage. Previous studies have used landslide susceptibility modelling (LSM) to analyse the relationship between coseismic landslides and tectonics, geology, hydrology and human activities, which is helpful in understanding the mechanism of coseismic occurrence for better disaster prevention. Here, the coseismic landslides caused by the Luding Mw 6.8 earthquake on 5 September 2022 provide us with an opportunity to further explore the occurrence patterns and the related factors influencing deep-cut valleys in the southeastern Tibetan Plateau. We considered 13 landslide conditioning factors (LCFs) and used four machine learning methods to conduct more than 1000 modelling analyses of the established coseismic landslide dataset and obtained a landslide susceptibility map of the study area. Specifically, the high hazardous landslide areas are mainly concentrated in the mid-altitude area (1000–2000 m), more than 92% are less than 150 m away from the road, more than 85% of the highly sensitive areas are less than 2 km away from the river network, and more than 70% of the highly sensitive areas are within 5 km of the seismogenic fault. Moreover, low-complexity algorithms are sufficient when using machine learning to model text-data coseismic landslides. Therefore, we recommend that the random forest and support vector machine algorithms might be better than the other two methods. Additionally, topography might be more influential than the fault hanging wall effect associated with the spatial distribution of coseismic landslides in deep-cut valleys in the southeastern Tibetan Plateau. [ABSTRACT FROM AUTHOR] |
| Copyright of Bulletin of Engineering Geology & the Environment is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 192427795 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Coseismic landslide susceptibility modelling via machine learning associated with the September 5, 2022, Luding Mw 6.8 earthquake, southeastern Tibetan Plateau. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Deng%2C+Lin%22">Deng, Lin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Hu%22">Wang, Hu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wanghu9905@126.com</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Kaijin%22">Li, Kaijin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shen%2C+Changwei%22">Shen, Changwei</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Bulletin+of+Engineering+Geology+%26+the+Environment%22">Bulletin of Engineering Geology & the Environment</searchLink>. Apr2026, Vol. 85 Issue 4, p1-15. 15p. – Name: Abstract Label: Abstract Group: Ab Data: Coseismic landslides have been widely studied due to their high occurrence and severe damage. Previous studies have used landslide susceptibility modelling (LSM) to analyse the relationship between coseismic landslides and tectonics, geology, hydrology and human activities, which is helpful in understanding the mechanism of coseismic occurrence for better disaster prevention. Here, the coseismic landslides caused by the Luding Mw 6.8 earthquake on 5 September 2022 provide us with an opportunity to further explore the occurrence patterns and the related factors influencing deep-cut valleys in the southeastern Tibetan Plateau. We considered 13 landslide conditioning factors (LCFs) and used four machine learning methods to conduct more than 1000 modelling analyses of the established coseismic landslide dataset and obtained a landslide susceptibility map of the study area. Specifically, the high hazardous landslide areas are mainly concentrated in the mid-altitude area (1000–2000 m), more than 92% are less than 150 m away from the road, more than 85% of the highly sensitive areas are less than 2 km away from the river network, and more than 70% of the highly sensitive areas are within 5 km of the seismogenic fault. Moreover, low-complexity algorithms are sufficient when using machine learning to model text-data coseismic landslides. Therefore, we recommend that the random forest and support vector machine algorithms might be better than the other two methods. Additionally, topography might be more influential than the fault hanging wall effect associated with the spatial distribution of coseismic landslides in deep-cut valleys in the southeastern Tibetan Plateau. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Bulletin of Engineering Geology & the Environment is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192427795 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10064-026-04864-9 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 15 StartPage: 1 Titles: – TitleFull: Coseismic landslide susceptibility modelling via machine learning associated with the September 5, 2022, Luding Mw 6.8 earthquake, southeastern Tibetan Plateau. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Deng, Lin – PersonEntity: Name: NameFull: Wang, Hu – PersonEntity: Name: NameFull: Li, Kaijin – PersonEntity: Name: NameFull: Shen, Changwei IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 14359529 Numbering: – Type: volume Value: 85 – Type: issue Value: 4 Titles: – TitleFull: Bulletin of Engineering Geology & the Environment Type: main |
| ResultId | 1 |
